Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of the word "so" that indicate reasoning or conclusions are being drawn

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.67
    MCA
    -0.60
     }^{[
    -0.58
    choly
    -0.58
     McColl
    -0.54
    OOT
    -0.54
     बाद
    -0.54
     later
    -0.54
     transfieras
    -0.53
     Administrativna
    -0.53
    POSITIVE LOGITS
    horabuena
    0.70
     maș
    0.66
    
    0.64
    WithIOException
    0.61
    berdayakan
    0.60
    TintMode
    0.60
     saja
    0.59
     grosir
    0.57
    Hozzáférés
    0.57
     forth
    0.57
    Act Density 0.093%

    No Known Activations